Addressing Imbalance for Class Incremental Learning in Medical Image Classification

TL;DR

This paper introduces two simple methods to address class imbalance in medical image class incremental learning, significantly reducing catastrophic forgetting and improving performance on benchmark datasets.

Contribution

The paper proposes a CIL-balanced classification loss and a distribution margin loss to effectively mitigate class imbalance issues in medical image incremental learning.

Findings

Outperforms state-of-the-art methods on three benchmark datasets.

Effectively reduces catastrophic forgetting in imbalanced medical datasets.

Enhances inter-class separation and intra-class compactness in embedding space.

Abstract

Deep convolutional neural networks have made significant breakthroughs in medical image classification, under the assumption that training samples from all classes are simultaneously available. However, in real-world medical scenarios, there's a common need to continuously learn about new diseases, leading to the emerging field of class incremental learning (CIL) in the medical domain. Typically, CIL suffers from catastrophic forgetting when trained on new classes. This phenomenon is mainly caused by the imbalance between old and new classes, and it becomes even more challenging with imbalanced medical datasets. In this work, we introduce two simple yet effective plug-in methods to mitigate the adverse effects of the imbalance. First, we propose a CIL-balanced classification loss to mitigate the classifier bias toward majority classes via logit adjustment. Second, we propose a distribution margin loss that not only alleviates the inter-class overlap in embedding space but also enforces the intra-class compactness. We evaluate the effectiveness of our method with extensive experiments on three benchmark datasets (CCH5000, HAM10000, and EyePACS). The results demonstrate that our approach outperforms state-of-the-art methods.